Pricing

from $0.70 / 1,000 page reads

Try for free

Go to Apify Store

RAG Web Browser - Google Search to Markdown for AI

Try for free

Web search and fetch for AI agents and RAG: searches Google and returns the top results as clean Markdown, or reads any URL. Main content only, token counts, metadata, any country and language, many queries per run. Plain HTTP, no browser: seconds per query.

Pricing

from $0.70 / 1,000 page reads

Rating

0.0

(0)

Developer

Eimantas V

Actor stats

Bookmarked

Total users

Monthly active users

5 days ago

Last modified

Categories

Record type

recordType

Optional

"item" for a page read (charged), "error" for a page or search that failed (never charged).

Type:string

Example:

item

Options:

itemerror

Query

input

Optional

The search or URL exactly as given in the input, so rows join back to it.

Type:string

Example:

what is retrieval augmented generation

Google result

searchResult

Optional

The Google result this page came from: rank, title, snippet, URL. Null when the query was a URL.

Type:object | null

Page metadata

metadata

Optional

The page's URL after redirects, title, description, language, canonical URL, author, dates, site name, image and Open Graph tags.

Type:object

Markdown

markdown

Optional

The page's content as Markdown (when the Markdown format is selected).

Type:string

Example:

# Retrieval-augmented generation **Retrieval-augmented generation** (**RAG**) is a technique...

Plain text

text

Optional

The page's content as plain text (when the Plain text format is selected).

Type:string

HTML

html

Optional

The cleaned HTML of the content, links made absolute (when the HTML format is selected).

Type:string

Links

links

Optional

Every link on the page in order, each once, as { url, text } with absolute URLs (when the Links format is selected).

Type:object[]

Words

wordCount

Optional

Words in the content returned.

Type:integer

Example:

2344

Tokens (estimate)

tokenCount

Optional

Estimated LLM tokens of the Markdown (or text): about 4 characters per token, 1 per CJK character.

Type:integer

Example:

5276

Truncated

contentTruncated

Optional

True when the content was cut at "Max characters per page", or the page was larger than 4 MB.

Type:boolean

Example:

false

Content scope

contentScope

Optional

"main" when the content was narrowed to the page's main content, "page" when the whole cleaned page is returned.

Type:string

Example:

main

Options:

mainpage

Crawl

crawl

Optional

How the page loaded: HTTP status, time, content type, and whether it was read (handled) or not (failed).

Type:object | null

Scraped at

scrapedAt

Optional

When the run started (ISO 8601).

Type:string

Example:

2026-10-29T15:04:05.000Z

Error code

errorCode

Optional

Error rows only: NO_RESULTS, RATE_LIMITED, BLOCKED, TIMEOUT, NOT_FOUND, HTTP_ERROR, NETWORK, UNSUPPORTED_CONTENT, INVALID_URL or PARSE_FAILED.

Type:string

Example:

NOT_FOUND

Error

errorMessage

Optional

Error rows only: what happened, in plain words.

Type:string

Example:

The page no longer exists (HTTP 404). Not charged.

URL

url

Optional

Error rows only: the page that could not be read (null when the search itself failed).

Type:string | null

Example:

https://example.com/missing

RAG Web Browser

apify/rag-web-browser

Web search and fetch tool for AI agents and RAG pipelines. It queries Google Search, scrapes the top N pages using a full web browser, and returns their content as clean Markdown for further processing by an LLM. Can also fetch individual URLs.

Apify

207K

4.7

(35)

Google Search Results Scraper - SERP API

eiv/google-search-scraper

Scrape Google search results by keyword or URL: organic results with real URLs and ranks, places, top stories, knowledge panel, related searches, News and Videos tabs. Optional AI Overview, People also ask and ads. Any country, language or city. From $0.40 per 1,000 pages.

Eimantas V

132

LinkedIn Jobs Scraper - Salaries, Applicants & Companies

eiv/linkedin-jobs-scraper

Scrape LinkedIn jobs by keyword, location, company or search URL: salary, applicants, seniority, job type, remote/hybrid, full description and company profile. Filters LinkedIn ignores are checked on every job and never charged. No login. From $0.60 per 1,000 jobs.

Eimantas V

Meta Ads Library Scraper (Pay per Event)

eiv/meta-ads-library-scraper

Scrape Meta Ad Library by keyword or Facebook page URL. Get ad text, CTA, headlines, platforms, languages, targeting, reach data, and delivery dates. Supports all countries, languages, and filters. Works with any Ad Library search URL. Lightning fast, structured JSON output.

Eimantas V

452

AI Web Crawler

hounderd/ai-web-crawler

Crawl websites and extract clean, LLM-ready markdown content with stealth browser rendering, anti-bot hardening, smart content filtering, and structured metadata extraction. Built for RAG pipelines, AI agents, and data workflows.

Hounderd

RAG Web Browser — Web Content for AI & LLMs

nexgendata/rag-web-browser

Web browser for RAG pipelines and AI agents. Searches DuckDuckGo, scrapes the top results, returns clean Markdown with citation URLs. Feed your LLM with real-time web data. Works with Claude, GPT, LangChain, CrewAI. No API key needed.

NexGenData

Eventbrite Scraper - Event Data: City, Date, Venue, Organizer

eiv/eventbrite-scraper

Eventbrite scraper for market research, event data. Search events by city, date, category, format, online or in-person. No login, no API key, no ticket prices - the feed has none. True UTC starts from local time + IANA timezone, venue coordinates, organizer IDs, publish date, coverage row per city.

Eimantas V

Instagram Post & Reel Scraper - Views & Engagement

eiv/instagram-post-scraper

Scrape Instagram posts and reels by profile, post URL or audio: exact likes, comments and views, captions, dates, engagement rate, collaborators, sponsors, tags, location, music and media URLs. Date-range and reels-only filters. No login. From $0.70 per 1,000 posts.

Eimantas V

RAG Web Browser Scraper

datapilot/rag-web-browser-scraper

RAG Web Browser Search & Crawl Actor uses to search Bing or crawl URLs, then extracts page content as clean markdown. It captures title, description, language, HTTP status, and structured metadata. Supports multiple queries, proxies, and outputs organized crawl + search results.

Data Pilot

RAG Web Browser — URL & Website to Markdown for LLM & RAG

s-r/rag-web-browser

Search the web or pass URLs and get each page as clean Markdown, plain text or HTML with title and source URL, ready for LLM and RAG pipelines. Crawls links up to 3 hops, up to 1000 URLs per run, pay only per converted page.